Pokémon Red via Reinforcement Learning

We present a Deep Reinforcement Learning (DRL) agent that successfully completes the first several hours of Pokémon Red, a classic Game Boy JRPG that exposes significant challenges as a testbed for agents, including multitasking, long horizons of tens of thousands of steps, hard exploration, and a vast array of potential policies. Our agent completes an initial segment of the game, up to Cerulean City, a location requiring progression through two cities, battle-filled passages, a maze-like cave, and defeating the first gym leader. Our experiments include various ablations that reveal vulnerabilities in reward shaping. We argue that long-form games like Pokémon hold strong potential for future research, presenting long-term coherent reasoning challenges absent from simpler arcade games. Our environment wrapper, training algorithm, human replay data, and pretrained agent are available at (REDACTED FOR REVIEW).